Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3496 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.9628. Min Act: -0.1700
Data Index: 8629069 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.5253. Min Act: -0.1700
Data Index: 8499683 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.6816. Min Act: -0.1700
Data Index: 559379 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9628. Min Range: -6.9628
Max Act: 5.9941. Min Act: -0.1700
Data Index: 499269 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.4003. Min Act: -0.1700
Data Index: 6877627 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.4003. Min Act: -0.1700
Data Index: 6150466 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.4003. Min Act: -0.1700
Data Index: 5916601 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.2753. Min Act: -0.1700
Data Index: 3994312 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.3691. Min Act: -0.1700
Data Index: 6150476 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.4003. Min Act: -0.1700
Data Index: 4623882 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.2753. Min Act: -0.1700
Data Index: 6560192 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.3066. Min Act: -0.1700
Data Index: 6922467 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.2128. Min Act: -0.1700
Data Index: 6420234 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.1816. Min Act: -0.1700
Data Index: 711239 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9628. Min Range: -6.9628
Max Act: 5.9316. Min Act: -0.1700
Data Index: 3589446 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.2128. Min Act: -0.1700
Data Index: 5045500 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.2128. Min Act: -0.1700
Data Index: 4443965 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.1191. Min Act: -0.1700
Data Index: 5211360 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.1503. Min Act: -0.1700
Data Index: 4406269 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9628. Min Range: -6.9628
Max Act: 6.1816. Min Act: -0.1700
Data Index: 3108399 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19